# Generalization error bounds for learning to rank: Does the length of document lists matter?

arXiv: https://arxiv.org/abs/1603.01860 · HTML: https://mlsanity.com/paper/1603.01860/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2016.

## Built on by (most cited first, 4 of 4)

- [Generalization Analysis for Contrastive Representation Learning](https://mlsanity.com/paper/2302.12383/) (2023)
- [Anchor Sampling for Federated Learning with Partial Client Participation](https://mlsanity.com/paper/2206.05891/) (2022)
- [Offline Model-Based Optimization by Learning to Rank](https://mlsanity.com/paper/2410.11502/) (2024)
- [On the Learnability of Multilabel Ranking](https://mlsanity.com/paper/2304.03337/) (2023)

## Abstract (arXiv)

We consider the generalization ability of algorithms for learning to rank at a query level, a problem also called subset ranking. Existing generalization error bounds necessarily degrade as the size of the document list associated with a query increases. We show that such a degradation is not intrinsic to the problem. For several loss functions, including the cross-entropy loss used in the well known ListNet method, there is no degradation in generalization ability as document lists become longer. We also provide novel generalization error bounds under ℓ1 regularization and faster convergence rates if the loss function is smooth.